Unsupervised Learning of Local Equivariant Descriptors for Point Clouds

Unsupervised Learning of Local Equivariant Descriptors for Point Clouds

Correspondences between 3D keypoints generated by matching local descriptors are a key step in 3D computer vision and graphic applications. Learned descriptors are rapidly evolving and outperforming the classical handcrafted approaches in the field. Yet, to learn effective representations they requi...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 12 vom: 09. Dez., Seite 9687-9702
1. Verfasser: Marcon, Marlon (VerfasserIn)
Weitere Verfasser: Spezialetti, Riccardo, Salti, Samuele, Silva, Luciano, Stefano, Luigi Di
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM33290380X
003 DE-627
005 20231225220532.0
007 cr uuu---uuuuu
008 231225s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2021.3126713  |2 doi 
028 5 2 |a pubmed24n1109.xml 
035 |a (DE-627)NLM33290380X 
035 |a (NLM)34752387 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Marcon, Marlon  |e verfasserin  |4 aut 
245 1 0 |a Unsupervised Learning of Local Equivariant Descriptors for Point Clouds 
264 1 |c 2022 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 08.11.2022 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Correspondences between 3D keypoints generated by matching local descriptors are a key step in 3D computer vision and graphic applications. Learned descriptors are rapidly evolving and outperforming the classical handcrafted approaches in the field. Yet, to learn effective representations they require supervision through labeled data, which are cumbersome and time-consuming to obtain. Unsupervised alternatives exist, but they lag in performance. Moreover, invariance to viewpoint changes is attained either by relying on data augmentation, which is prone to degrading upon generalization on unseen datasets, or by learning from handcrafted representations of the input which are already rotation invariant but whose effectiveness at training time may significantly affect the learned descriptor. We show how learning an equivariant 3D local descriptor instead of an invariant one can overcome both issues. LEAD (Local EquivAriant Descriptor) combines Spherical CNNs to learn an equivariant representation together with plane-folding decoders to learn without supervision. Through extensive experiments on standard surface registration datasets, we show how our proposal outperforms existing unsupervised methods by a large margin and achieves competitive results against the supervised approaches, especially in the practically very relevant scenario of transfer learning 
650 4 |a Journal Article 
700 1 |a Spezialetti, Riccardo  |e verfasserin  |4 aut 
700 1 |a Salti, Samuele  |e verfasserin  |4 aut 
700 1 |a Silva, Luciano  |e verfasserin  |4 aut 
700 1 |a Stefano, Luigi Di  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 44(2022), 12 vom: 09. Dez., Seite 9687-9702  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:44  |g year:2022  |g number:12  |g day:09  |g month:12  |g pages:9687-9702 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2021.3126713  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 44  |j 2022  |e 12  |b 09  |c 12  |h 9687-9702